© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43176
    Prev
    Next
    INDEX
    Explanations

    each sentence offering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pente
    0.50
     estos
    0.46
     दैन
    0.45
    feels
    0.44
    ﺖ
    0.44
     five
    0.44
     evenings
    0.44
     scent
    0.43
     Hern
    0.42
     lid
    0.42
    POSITIVE LOGITS
    CapsLock
    0.46
     Compress
    0.45
     만들어
    0.44
    cartes
    0.43
     ஸ்ப
    0.41
    シューズ
    0.41
    дир
    0.41
    鐲
    0.40
    ън
    0.40
    產生
    0.40
    Activations Density 0.001%

    No Known Activations